Mispronunciation Detection Without L2 Pronunciation Dataset in Low-Resource Setting: A Case Study in Finland Swedish

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

Proceedings of the Interspeech 2025, pp. 2435-2439, Proceedings of the Annual Conference of the International Speech Communication Association

Abstract

Mispronunciation detection (MD) models are the cornerstones of many language learning applications. Unfortunately, most systems are built for English and other major languages, while low-resourced language varieties, such as Finland Swedish (FS), lack such tools. In this paper, we introduce our MD model for FS, trained on 89 hours of first language (L1) speakers' spontaneous speech and tested on 33 minutes of L2 transcribed read-aloud speech. We trained a multilingual wav2vec 2.0 model with entropy regularization, followed by temperature scaling and top-k normalization after the inference to better adapt it for MD. The main novelty of our method lies in its simplicity, requiring minimal L2 data. The process is also language-independent, making it suitable for other low-resource languages. Our proposed algorithm allows us to balance Recall (43.2%) and Precision (29.8%), compared with the baseline model's Recall (77.5%) and Precision (17.6%).

Description

Other note

Citation

Phan, N, Kuronen, M, Kautonen, M, von Zansen, A, Getman, Y, Voskoboinik, E, Grósz, T & Kurimo, M 2025, Mispronunciation Detection Without L2 Pronunciation Dataset in Low-Resource Setting: A Case Study in Finland Swedish. in Proceedings of the Interspeech 2025. Proceedings of the Annual Conference of the International Speech Communication Association, International Speech Communication Association (ISCA), pp. 2435-2439, Interspeech, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-1375